Shooting method for splicing document images

A text image and shooting method technology, applied in the field of image processing, can solve problems such as missing corners, time-consuming, empty documents, etc.

Active Publication Date: 2012-07-04
SHANGHAI HEHE INFORMATION TECH DEV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, one disadvantage of this solution is that sometimes the partial document image taken by the user does not completely cover all areas of the document, resulting in holes or missing corners in the final spliced ​​document image
If it is found that the final stitched full image is incomplete, retake all the partial images and stitch them again, which will be very time-consuming

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Shooting method for splicing document images
  • Shooting method for splicing document images
  • Shooting method for splicing document images

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0063] The present invention proposes a shooting method for text image splicing. The method first requires the user to keep the camera relatively far away from the document, that is, just enough to capture the entire document image, and use the entire document image as a template image, and then According to the template image, the user is prompted to take pictures of each part of the document in turn. At this time, when taking a partial image, the camera is closer, and the text image will be clearer. Each part forms a partial image, and during the shooting process It is possible to see the document area covered by the captured partial images, so as to finally ensure that all the captured partial images can cover the entire document, so that there will be no holes or missing corners in the final stitched document image.

[0064] see figure 1 , the present invention is used for the shooting method of text image splicing and specifically comprises the following steps:

[0065] ...

Embodiment 2

[0086] This embodiment discloses a shooting method for text image stitching, the method comprising:

[0087] Step 110, photographing the entire document, and the obtained entire text image is used as a document template image.

[0088] Step 120, according to the shooting prompt, take a partial image of a certain area of ​​the document.

[0089] Step 130, performing feature matching on the captured local area image and the template text image; the method for performing feature matching on the local image and the template image includes: Step 131, determining the feature key point of interest; Step 132, extracting the area around the key point The feature vector descriptor; step 133, match each feature vector descriptor by the Euclidean distance of feature points; in step 133, the matching strategy adopts the nearest neighbor ratio matching: for the feature point matching of two images, it is necessary to search The corresponding matching point of a feature point in the image, ...

Embodiment 3

[0101] This embodiment discloses a shooting method for text image stitching, the method comprising:

[0102] Step S1, photographing the entire document, and the obtained entire text image is used as a template image.

[0103] Step S2, according to the shooting prompt, take a partial image of a certain area of ​​the document.

[0104] Step S3, performing feature matching on the captured local area image and the template text image.

[0105] Step S4, determine whether the feature matching is successful; after the matching is successful, calculate the perspective change matrix that changes the local image to the template text image through the matching feature points obtained in step S3; calculate the inscribed matrix formed by the four vertices through the perspective change matrix rectangle.

[0106] Step S5, according to the inscribed rectangle obtained by each shooting, calculate the coverage area of ​​the successful shooting, and judge whether all the successfully shooting...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a shooting method for splicing document images, which comprises the following steps of: shooting an entire document; shooting a local image of a certain area of the document; performing characteristic matching on the shot local area image and a document pattern image; calculating a perspective change matrix reflecting the change of the local image to the document pattern image by using obtained matched characteristic points; calculating an inscribed rectangle consisting of four vertexes by using the perspective change matrix; calculating successfully shot coverage areas by using the inscribed rectangles obtained by the shooting of each time, and judging whether all the successfully shot areas cover the whole pattern image or not; if the successfully shot areas cover the whole pattern image, finishing the shooting; and if the successfully shot areas do not cover the whole pattern image, resolving the areas which are not shot or shot unsuccessfully from the successfully shot areas, and continuing the shooting. The shooting method ensures all the shot local images can cover the whole document area so as to avoid holes and unfilled corners in the finally spliced document image.

Description

technical field [0001] The invention belongs to the technical field of image processing, and relates to a shooting method, in particular to a shooting method for text image splicing. Background technique [0002] With the development of technology, today's smart phones are generally integrated with a digital camera function with auto focus. People often use the camera on the mobile phone to scan or take text images, because the camera on the mobile phone is generally between three million With a resolution of up to 5 million pixels, the clarity and resolution of the text images captured cannot be compared with traditional scanners. Therefore, in order to obtain a high-resolution full picture of the document, a common solution is to bring the camera closer to the document, first take pictures of various local areas of the document, and then stitch these partial images together after obtaining a clearer partial text image , to generate a full text image. In this way, the res...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Patents(China)
IPC IPC(8): G03B37/00G06T7/40
Inventor 黄灿龙腾镇立新
Owner SHANGHAI HEHE INFORMATION TECH DEV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap